The Stack Overflow Podcast

Your LLM issues are really data issues

Tue, 28 Apr 2026 04:00:00 -0000

Ryan welcomes Harsha Chintalapani, co-founder and CTO at Collate and co-creator of Open Metadata, to the show to discuss why AI and LLMs struggle with real-time, structured production data. They explore how schema changes, inconsistent definitions (like “customer”), and weak governance can break both your analytics and MLs, and what companies can do to get their data AI-ready, from metadata management to observability.

Episode Notes:

Collate is a semantic intelligence platform built on a semantic metadata graph for discovery, governance, and AI observability across your data ecosystem.

Connect with Harsha on LinkedIn.

Congrats to user buttonsrtoys, who won a Famous Question badge for their question Possible to edit PDF without embedded font installed?.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Lights, camera, open source!

Fri, 24 Apr 2026 04:00:00 -0000

Ryan is joined on the show by Cult.Repo producers Emma Tracey and Josiah Mcgarvie to discuss making documentaries about open-source software and the people behind the major technologies that uphold the internet. They explore why open-source projects and the people who maintain them are such interesting stories for audiences, how being outsiders has helped them tell these community stories, and what they see as the common stressors that plague all open-source projects, such as sustainability, compensation, and burnout.

Episode notes:

Cult.Repo produces documentaries and shorts about the human stories behind open-source technology. Check out their filmography on their YouTube channel.

Have an idea for an open-source community they should cover? Email the Cult.Repo team at hello@cultrepo.com.

Shoutout to user kiranvj for winning a Populist badge for their answer to What is a good way to automatically bind JS class methods?.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

How to get multiple agents to play nice at scale

Wed, 22 Apr 2026 04:00:00 -0000

We still need developer communities

Tue, 21 Apr 2026 04:00:00 -0000

Ryan welcomes Mike Swift, co-founder and CEO of Major League Hacking, to the show to chat about the never-ending need for software developer communities and entry points into programming; MHL’s recent acquisition of DEV and how they’re creating a place for shared knowledge, building, and publishing; and why now is the best time to be both an artisan and a builder in a world with AI software development tools.

Episode notes:

Major League Hacking is a 500k+ global member community that hosts hackathons and open-source fellowships for the next generation of developers. They recently acquired DEV, an online community for 3M+ developers to learn and share together.

Connect with Mike on LinkedIn or email him at swift@mhl.io.

Congrats to Stellar Answer badge winner Antony Hatchkins for getting over a hundred saves on their answer to Git replacing LF with CRLF.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

No country left behind with sovereign AI

Fri, 17 Apr 2026 04:00:00 -0000

Ryan welcomes Stephen Watt, distinguished engineer and VP of Red Hat’s Office of the CTO, to chat about digital sovereignty and sovereign AI. They explore major infrastructure constraints for things like power, cooling, and scarce hardware that cause the regional disparities we see in sovereign AI, plus why we need to extend Kubernetes and integrate PyTorch Stack not just for a sovereign cloud but for sovereign AI.

Episode notes:

Red Hat’s Office of the CTO is a division of 150 software engineers and researchers working on their Research and Emerging Technologies arms, helping to shape the vision and strategy of Red Hat’s technology.

Connect with Stephen on LinkedIn.

Congrats to user Ittiel for winning a Populist badge on their answer to Print timestamps in Docker Compose logs.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Who needs VCs when you have friends like these?

Tue, 14 Apr 2026 04:00:00 -0000

Ryan welcomes RunPod co-founder and CEO Zhen Lu to discuss circumventing VC money by going straight to your community for funding, how Zhen balances founder intuition with user feedback when the community is the one backing the project, and RunPod’s journey from basement servers to global infrastructure partnerships with a software-layer approach and data-first paradigm.

Episode notes:

RunPod is an end-to-end AI cloud that provides developers with GPUs so they can build and run custom AI systems that scale.

Connect with Zhen on LinkedIn or email him at zhenlu@runpod.io.

Today’s shoutout goes to Famous Question badge winner cigol on, who won the badge for getting 10,000+ views on their question Using JavaScript, is it possible to capture the body payload from an outgoing fetch request?.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

The messy truth of your AI strategies

Fri, 10 Apr 2026 04:00:00 -0000

Ryan welcomes Hema Raghavan, co-founder and head of engineering at Kumo.ai, to dive into all the messy stuff that comes with implementing AI, from pipeline sprawl to shadow AI. They discuss governance approaches like deploying models inside approved platforms and routing calls through monitored gateways, and how broken pipelines from complex feature-engineering motivated Kumo.ai’s approach of using a single foundation model with on-the-fly database queries.

Episode notes:

Kumo.ai allows you to train and run state-of-the-art AI models on your relational data, allowing you to make predictions about your users and transactions in seconds.

Connect with Hema on LinkedIn or reach out to her at her email hema@kumo.ai.

Congrats to user BalusC for winning a Populist badge on their answer to How to sanitize HTML code to prevent XSS attacks in Java or JSP?.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

He designed C++ to solve your code problems

Tue, 07 Apr 2026 04:00:00 -0000

Ryan welcomes Bjarne Stroustrup, designer of C++ and professor at Columbia, to the show to dive into all things C++, from its history to where it's going today. They discuss its first emergence as a way to bridge high-level abstractions with low-level systems control, the criticisms some have around memory safety and null pointers (and how to solve these problems in your code), and why “move to Rust” thinking is too simplistic for modern codebases.

Episode notes:

Keep up with everything happening with C++ at the Standard C++ Foundation’s website.

Connect with Bjarne on LinkedIn and explore more of his work at his website.

Congrats to Populist badge winner Michael Sorens for winning the badge for their answer to PowerShell equivalent for "head -n-3"?.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Seizing the means of messenger production

Fri, 03 Apr 2026 04:00:00 -0000

Ryan sits down with Galen Wolfe-Pauly, CEO of Tlon, to chat about calm computing and how humans can take back ownership of their data and digital world. They discuss the early internet’s evolution from individual creativity into today’s internet that turns users into products, Galen’s takeaways from building a new network architecture that prioritizes user control, and why messenger applications are ripe for decentralization.

Episode notes:

Tlon is releasing a decentralized messenger app that gives you ownership of your data, built on Urbit, a complete, wholly encapsulated system that allows you to run a personal server in the cloud. Use the code STACK to skip the waitlist for the Tlon Messenger app.

Connect with Galen on LinkedIn.

Shoutout to user mkobuolys for winning a Populist badge for their answer to Set default transition for go_router in Flutter.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

How can you test your code when you don’t know what’s in it?

Tue, 31 Mar 2026 04:30:00 -0000

Ryan hosts SmartBear’s VP of AI and Architecture Fitz Nowlan to explore how we’re moving away from old assumptions about software development, the challenges of testing MCP servers as LLM-driven agents introduce non-determinism that breaks tradition, and how data locality and data construction are becoming more valuable when source code is so easy to generate.

Episode notes:

SmartBear gives devs tools for application performance monitoring, software development, software testing, and API management—all at AI speed and scale.

Connect with Fitz on LinkedIn and email him at FitzNowlan@SmartBear.com

Congrats to Great Answer winner Alexander for winning the badge for their answer to Is there a way to make Runnable's run() throw an exception?.

TRANSCRIPT

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.